Skip to content

Instantly share code, notes, and snippets.

View un1t's full-sized avatar

Ilya Shalyapin un1t

View GitHub Profile
@un1t
un1t / elasticsearch_ru_stemming_and_morphology.py
Created March 10, 2016 12:10 — forked from svartalf/elasticsearch_ru_stemming_and_morphology.py
Example of the ElasticSearch configuration for russian stemming and morphology
requests.put('http://localhost:9200/site/', data=json.dumps({
'settings': {
'analysis': {
'analyzer': {
'ru': {
'type': 'custom',
'tokenizer': 'standard',
"filter": ['lowercase', 'russian_morphology', 'english_morphology', 'ru_stopwords'],
},
},
@un1t
un1t / abcnum_converter.py
Created April 6, 2016 18:56
Converting an Integer to a String in Any Base
import string
# http://interactivepython.org/runestone/static/pythonds/Recursion/pythondsConvertinganIntegertoaStringinAnyBase.html
class AbcNumCoverter:
chars = string.digits + string.ascii_lowercase
base = len(chars)
@classmethod
def to_str(cls, n):
cluster.name: mycluster
node.name: node-1
node.master: true
node.data: true
network.host: 0.0.0.0
transport.tcp.port: 9300
http.port: 9200
@un1t
un1t / logging-settings.py
Created June 30, 2016 08:25
django logging settings
LOGGING = {
'version': 1,
'disable_existing_loggers': True,
'formatters': {
'verbose': {
'format': '%(levelname)s %(asctime)s %(process)d %(module)s %(message)s'
},
'simple': {
'format': '%(levelname)s %(message)s'
},
import gc
from more_itertools import chunked
from collections import defaultdict
def fetch_fk(fk_field, fields, objects):
assert 'id' in fields
if not objects:
return
from django import forms
from django.db import models
class BitFieldWrapper:
def __init__(self, instance, field, value):
self.instance = instance
self.field = field
self.value = value
@un1t
un1t / SIREn Join
Created October 22, 2016 12:27
SIREn Join Plugin for Elasticsearch Example
curl -XPUT 'http://localhost:9200/_bulk?pretty' -d '
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "1" } }
{ "title" : "The NoSQL database glut", "journal" : "2", "author": "1" }
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "2" } }
{ "title" : "Graph Databases Seen Connecting the Dots", "journal" : "1", "author": "2"}
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "3" } }
{ "title" : "How to determine which NoSQL DBMS best fits your needs", "journal" : "2", "author": "3" }
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "4" } }
{ "title" : "MapR ships Apache Drill", "journal" : "4", "author": "4" }
@un1t
un1t / RapidXmlExample.c
Created November 14, 2016 19:30 — forked from JSchaenzle/RapidXmlExample.c
RapidXml example parsing beer journal
#include <string.h>
#include <stdio.h>
#include <iostream>
#include <fstream>
#include <vector>
#include "rapidxml-1.13/rapidxml.hpp"
using namespace rapidxml;
using namespace std;
curl -XPUT 'http://localhost:9200/_bulk?pretty' -d '
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "1" } }
{ "title" : "The NoSQL database glut", "journal" : "2", "author": [{"title": "August S"}, {"title": "Weiss P L"}] }
{ "index" : { "_index" : "test", "_type" : "publication", "_id" : "2" } }
{ "title" : "Graph Databases Seen Connecting the Dots", "journal" : "1", "author": [{"title": "Weiss S"}] }
'
curl -XGET 'http://localhost:9200/test/_search?pretty' -d '{"query": {"match": {"author.title": {"query": "weiss s", "operator": "and"}}}}'
# curl -XDELETE 'http://localhost:9200/test'
curl -XPUT 'http://localhost:9200/test' -d '
{
"analysis": {
"char_filter": {
"my_charfilter": {
"type": "mapping",
"mappings": ["Ё=>Е", "ё=>е"]
}